Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    key-value pairs separated by commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Paper
    0.42
     fields
    0.40
    Branch
    0.39
     racing
    0.39
    체가
    0.39
     models
    0.38
    Issues
    0.38
     nothing
    0.37
     ruling
    0.37
     Racing
    0.37
    POSITIVE LOGITS
     seer
    0.41
    mesi
    0.41
    thati
    0.39
     assayed
    0.39
    $",
    0.38
     ప్రా
    0.37
    ក្ខ
    0.37
    mesinin
    0.37
    埤
    0.37
     Ov
    0.36
    Act Density 0.000%

    No Known Activations